汇报题目：INDIN’19 参会报告

汇报时间：2019年8月2日(星期五) 19:00

汇报地点：科技园 西五楼 北楼A228会议室

汇报人：潘彤阳

会议名称：IEEE International Conference on Industrial Informatics, INDIN’19

会议时间：22-25 July, 2019

会议地点：Helsinki-Espoo, Finland

会议简介：IEEE INDIN international conference provides a forum for presentation and discussion of the state-of-art and future perspectives of industrial information technologies. Industry experts, researchers and academics are gathering together to share ideas and experiences surrounding frontier technologies, breakthroughs, innovative solutions, research results, as well as initiatives related to industrial informatics and their applications.

参加论文信息

Title: An Adversarial Learning Framework for Zero-shot Fault Recognition of Mechanical Systems

Author: Jinglong Chen, Tongyang Pan, Zitong Zhou, Shuilong He

Abstract: Data imbalance is a major problem in intelligent fault diagnosis. Aiming at this problem, the paper proposed a novel adversarial learning framework for zero-shot fault recognition of mechanical systems. The proposed network consists of three parts which are the feature extractor, the generator and the discriminator. Trained with normal samples, the proposed method is capable of generating unseen fault samples by changing the condition of the generator. After, these synthetic samples are used to train an improved deep neural network for fault recognition. Results show that the proposed method can recognize the unseen faults even though none of fault samples are available during training, which is meaningful for industry application